INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orc

-0.80

irgin

-0.70

quickShipAvailable

-0.70

 Shen

-0.69

escal

-0.65

ceans

-0.65

ente

-0.63

english

-0.63

aura

-0.63

 Rossi

-0.61

POSITIVE LOGITS

abus

0.98

efully

0.65

 Afgh

0.62

istic

0.60

agy

0.60

hap

0.59

owicz

0.59

erk

0.58

=#

0.58

aph

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.